6 papers
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
Zhihao Yang, Haojin Wang, Juncheng Wu +7
Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whether models c…
MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models
Haojin Wang, Yike Wang, Shangbin Feng +2
Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities, but their solutions are often verbose and computationally expensive, and taxing for users to read…
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Dylan Zhang, Yufeng Xu, Haojin Wang +2
Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement learning (RL) stage. However, SFT is often…
MoCo: A One-Stop Shop for Model Collaboration Research
Shangbin Feng, Yuyang Bai, Ziyuan Yang +17
Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, an…
MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning
Suhao Yu, Haojin Wang, Juncheng Wu +9
Real-world clinical practice demands multi-image comparative reasoning, yet current medical benchmarks remain limited to single-frame interpretation. We present MedFrameQA, the fir…
Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
Haojin Wang, Zining Zhu, Freda Shi
Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt. In this work, we attempt to systematically understand…